© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 108599
    Prev
    Next
    INDEX
    Explanations

    Life sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     barter
    -0.08
     utens
    -0.08
     namespace
    -0.08
     doucement
    -0.08
     merchants
    -0.08
     liberated
    -0.08
    _namespace
    -0.08
     aromas
    -0.08
    举办
    -0.08
     délic
    -0.07
    POSITIVE LOGITS
     മരണ
    0.10
     terrifying
    0.10
     horr
    0.10
     horrific
    0.10
     ölüm
    0.09
     death
    0.09
     heartbreaking
    0.09
     horrifying
    0.09
     muerte
    0.09
     मृत्यु
    0.09
    Activations Density 0.019%

    No Known Activations